Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Son, Ha Min, Ren, Huan, Liu, Xin, Zhao, Zhe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914437614534656
author Son, Ha Min
Ren, Huan
Liu, Xin
Zhao, Zhe
author_facet Son, Ha Min
Ren, Huan
Liu, Xin
Zhao, Zhe
contents Android is the largest mobile platform, yet automatically building applications remains a practical challenge. While Large Language Models (LLMs) show promise for code repair, their use for fixing Android build errors remains underexplored. To address this gap, we first introduce AndroidBuildBench, a benchmark of 1,019 build failures curated from the commit histories of 43 open-source Android projects. Each problem is paired with a verified solution from a subsequent commit, ensuring that fixes are feasible. Second, we propose GradleFixer, an LLM agent with domain-specific tools for inspecting and manipulating the Gradle build environment. GradleFixer achieves a resolve rate of 81.4% (pass@1), significantly outperforming a state-of-the-art coding agent that relies on a general-purpose shell. GradleFixer's success suggests that while LLMs possess the high-level knowledge to solve these failures, they struggle to translate this knowledge into effective low-level actions using a general-purpose shell. We demonstrate the effectiveness of a strategy we term Tool Bridging, which replaces general-purpose shell commands with domain-aware abstractions. We hypothesize this approach works through two mechanisms: 1) it provides tools in an API-like format that LLMs use more reliably, and 2) it constrains the action space to relevant operations. This approach bridges the gap between the model's high-level reasoning and effective low-level execution.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08640
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
Son, Ha Min
Ren, Huan
Liu, Xin
Zhao, Zhe
Software Engineering
Artificial Intelligence
Android is the largest mobile platform, yet automatically building applications remains a practical challenge. While Large Language Models (LLMs) show promise for code repair, their use for fixing Android build errors remains underexplored. To address this gap, we first introduce AndroidBuildBench, a benchmark of 1,019 build failures curated from the commit histories of 43 open-source Android projects. Each problem is paired with a verified solution from a subsequent commit, ensuring that fixes are feasible. Second, we propose GradleFixer, an LLM agent with domain-specific tools for inspecting and manipulating the Gradle build environment. GradleFixer achieves a resolve rate of 81.4% (pass@1), significantly outperforming a state-of-the-art coding agent that relies on a general-purpose shell. GradleFixer's success suggests that while LLMs possess the high-level knowledge to solve these failures, they struggle to translate this knowledge into effective low-level actions using a general-purpose shell. We demonstrate the effectiveness of a strategy we term Tool Bridging, which replaces general-purpose shell commands with domain-aware abstractions. We hypothesize this approach works through two mechanisms: 1) it provides tools in an API-like format that LLMs use more reliably, and 2) it constrains the action space to relevant operations. This approach bridges the gap between the model's high-level reasoning and effective low-level execution.
title Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2510.08640